AI Agent Skills

Easegen is an open-source digital human course creation platform offering comprehensive solutions from course production and video management to intelligent quiz generat…

Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability

Video generation from text&image, 1st-gen

[NeurIPS 2024] A Generalizable World Model for Autonomous Driving

Smarter data pipelines for audio.

[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"

[CVPR 2025] "Towards Universal Soccer Video Understanding".

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

Real-time 3D face tracking and reconstruction from 2D video

[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

A Python package to stabilize videos using OpenCV

.NET Standard wrapper for FFmpeg. It allows to process media without know how FFmpeg works, and can be used to pass customized arguments to FFmpeg from dotnet core appli…

A command-line application to convert images, PDFs, and audio files to text using Apple's APIs

Video++, a C++14 high performance video and image processing library.

[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”

Generating Videos with Scene Dynamics. NIPS 2016.